JP7424515B2 - Object detection system, object detection method, and data sorting device - Google Patents

Description

The present invention relates to a technique for allocating propagation path information for object detection to a plurality of object detection devices in an object detection system that detects objects within a communication area from propagation path information of wireless signals communicated between wireless devices.

Conventionally, in systems that detect objects within a communication area from propagation path information of wireless signals communicated between wireless devices, object detection is performed by installing a detection device near the location where object detection is performed (for example, , see Non-Patent Document 1). In addition, as an example of propagation path information communicated between wireless devices, in a wireless LAN (Local Area Network) system, an AP (Access Point) transmits a reference signal to an STA (STAtion) to measure the state of the propagation path. However, propagation path information measured by the STA is transmitted to the AP (for example, see Non-Patent Document 2). Conventional detection devices can detect objects within a communication area by monitoring propagation path information transmitted from STA to AP, but in the method of Non-Patent Document 1, one of the detection devices is It is necessary to install it near the

On the other hand, for example, in wireless sensing using machine learning, in order to improve accuracy and perform high-performance sensing such as counting people, it is necessary to increase the amount of data for the learning model or to use more data for judgment. is necessary. However, when performing wireless sensing with a single device as in the past, the installation location of the detection device poses a problem. If only low-performance detection devices can be used due to constraints on the installation location, increasing the amount of learning data or data used for determination will increase the time required for determination. On the other hand, in the case of high-performance detection devices, it is easy to improve functionality and detection accuracy, but the size of the device increases, which places restrictions on where it can be installed. Furthermore, when a high-performance detection device is installed in a remote location to avoid restrictions on installation location, a problem arises in that it takes time to transfer data and the like.

“Evaluation for advancing wireless sensing technology for intelligent space formation”, B5-24, 2020 IEICE Society Conference, September 2020 H. Yu and T. Kim, “Beamforming transmission in IEEE 802.11ac under time-varying channels,” The Scientific World J., vol. 2014, pp. 1-11, Jul. 2014, article ID 920937.

With conventional technology, one of the devices that performs object detection needs to be installed near the detection location, and sufficient detection capability cannot be obtained due to the installation location and power supply, making it difficult to perform highly accurate object detection. Have difficulty. To avoid this, there is a method of installing the detection device at a location far from the detection target, but there are problems such as the time it takes to transfer data and the need for a high-speed communication line.

As described above, there is already a mechanism to detect the moving direction of an object using radio waves between wireless stations, including wireless LAN, but it is difficult to use with low accuracy and It has been difficult to perform simple object detection and high-precision/advanced object detection at the same time.

When detecting an object within a communication area from the propagation path information of a wireless signal, the present invention distributes the propagation path information for object detection to multiple object detection devices. The object of the present invention is to provide an object detection system, an object detection method, and a data sorting device that can achieve both accurate object detection and high-precision, advanced object detection that does not require real-time performance.

The object detection system according to the present invention includes a capture device that captures propagation path information measured and communicated between two or more wireless devices, and a first detection device that transmits a part of the propagation path information captured by the capture device. , a distributing device that distributes all of the propagation path information to a second detecting device, and the first detecting device divides the propagation path information based on part of the propagation path information distributed from the distributing device. The second detection device detects an object within a communication area between wireless devices, and the second detection device detects an object with higher accuracy and higher accuracy than the first detection device based on all the propagation path information distributed from the distribution device. The present invention is characterized in that it performs functional processing and detects objects within the communication area between the wireless devices.

The object detection method according to the present invention includes a capture device that captures propagation path information measured and communicated between two or more wireless devices, and a first detection device that transmits a part of the propagation path information captured by the capture device. , a distributing device that distributes all of the propagation path information to a second detecting device, and the first detecting device divides the propagation path information based on part of the propagation path information distributed from the distributing device. The second detection device detects an object within a communication area between wireless devices, and the second detection device detects an object with higher accuracy and higher accuracy than the first detection device based on all the propagation path information distributed from the distribution device. The present invention is characterized in that it performs functional processing and detects objects within the communication area between the wireless devices.

The data distribution device according to the present invention includes a first detection device and a second detection device that detect an object within a communication area between two or more wireless devices based on propagation path information measured and communicated between the two or more wireless devices. In the data distribution device that distributes the propagation path information captured by the capture device to the device, a part of the captured propagation path information is transmitted to the first detection device in real time, and the data distribution device distributes the propagation path information captured by the capture device to the device. The second detection device is characterized by having a distribution unit that transmits all of the captured propagation path information in real time or non-real time.

The object detection system, object detection method, and data distribution device according to the present invention provide propagation path information for object detection to a plurality of object detection devices when detecting an object within a communication area from propagation path information of a wireless signal. By sorting, it is possible to achieve both low-accuracy, simple object detection that requires real-time performance and high-accuracy, advanced object detection that does not require real-time performance.

FIG. 1 is a diagram illustrating an example of an object detection system according to an embodiment. FIG. 3 is a diagram illustrating an example of a sequence of wireless signals communicated between an AP and an STA. FIG. 3 is a diagram showing a sequence example of the object detection method according to the present embodiment. FIG. 3 is a diagram showing an example of a format stored in a storage device. FIG. 2 is a diagram illustrating an example of compressed CSI transmitted from an STA to an AP.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of an object detection system, an object detection method, and a data sorting device according to the present invention will be described with reference to the drawings. Here, the object detection system according to the present invention measures propagation path information (referred to as CSI (Channel State Information) in the embodiment) between at least two wireless devices such as a base station device and a terminal device, and outputs the measurement results. This is a system that uses a wireless communication system to capture CSI communicated between wireless devices and detect objects within the communication area of the wireless communication system. In the following embodiments, a case will be described in which the wireless communication system is a wireless LAN system, but the present invention is similarly applicable to any system that communicates by measuring the state of a propagation path.

FIG. 1 shows an example of an object detection system 100 according to an embodiment. In FIG. 1, an AP 101 corresponding to a base station device and an STA 102 corresponding to a terminal device perform communication compatible with the wireless LAN standard 802.11ac.

In FIG. 1, AP 101 has four antennas (AT(1), AT(2), AT(3), and AT(4)). Note that although the AP 101 shown in FIG. 1 has four antennas, it is sufficient to have two or more antennas. Further, it is assumed that the STA 102 is equipped with at least one antenna. Furthermore, although FIG. 1 shows an example in which there is one STA 102, this embodiment can also be applied when performing MU-MIMO (Multi User Multiple Input Multiple Output) transmission between the AP 101 and multiple STAs 102. be.

In FIG. 1, the AP 101 transmits a VHT NDP (Very High Throughput Null Data Packet) to the STA 102 as a reference signal for measuring the state of each propagation path between each antenna of the AP 101 and the STA 102. Then, the STA 102 calculates CSI indicating the state of the propagation path between each antenna of the AP 101 and the STA 102 from the VHT NDP, stores the result in a VHT Compressed BeamForming Report frame, and transmits it to the AP 101. The AP 101 performs transmission beam forming processing and the like based on the CSI received from the STA 102. Note that signals transmitted and received between the AP 101 and the STA 102 will be described later.

In FIG. 1, an object detection system 100 according to this embodiment includes a capture device 103, a sorting device 104, a storage device 105, a detection device 106(1), and a detection device 106(2).

The capture device 103 is installed near the communication area including the communication area between the AP 101 and the STA 102, monitors wireless LAN frames communicated between the AP 101 and the STA 102, and captures specific frames set in advance. . The capture device 103 determines a VHT Compressed Beamforming Report frame transmitted from the STA 102 to the AP 101 among the wireless LAN frames communicated between the AP 101 and the STA 102, and captures the frame. The frame in which the captured compressed CSI is stored and information on the reception time of the frame are transmitted to the distribution device 104. Here, CSI measurement and transmission are performed periodically between the AP 101 and the STA 102.

The distribution device 104 transmits information about the frame in which the compressed CSI captured by the capture device 103 is stored and the reception time of the frame to the detection device 106(1) and the detection device 106(2). The distribution device 104 also uses information obtained from the frame containing the compressed CSI received from the capture device 103 (source address, destination address, number of the capture device 103, acquired CSI, etc.) and the reception time of the frame. information (hereinafter, this information will be referred to as capture information as necessary) is stored in the storage device 105.

Here, the sorting device 104 transmits a part of the capture information captured by the capture device 103 to the detection device 106(1) in real time, and transmits all of the captured information to the detection device 106(1) in real time or non-real time. 2) Send to.

Note that as a method of transmitting a part of the captured information to the detection device 106(1), instead of transmitting it every time the above-mentioned frame is captured, the number of times of transmission may be reduced, such as once every few times. , each time the above-mentioned frame is captured, a part of the plurality of CSIs stored in the captured frame may be selected and transmitted to the detection device 106(1).

Further, as a method of transmitting all of the capture information to the detection device 106 (2), capture information may be transmitted to the detection device 106 (2) every time a frame is captured, or the capture information may be transmitted to the detection device 106 (2) at a predetermined period of time. The captured information stored in the storage device 105 may be read out at intervals or at predetermined times and transmitted all at once to the detection device 106(2).

Note that the sorting device 104 may be integrated with the capture device 103. Here, a program corresponding to the processing performed by the distribution device 104 may be executed by a general-purpose computer or an integrated circuit such as an FPGA (Field Programmable Gate Array). Further, the program may be provided recorded on a storage medium or may be provided through a network.

The storage device 105 is composed of a hard disk, a memory, etc., and stores capture information transmitted from the capture device 103 to the distribution device 104. Note that the storage device 105 may be integrated as a storage section of the distribution device 104.

The detection device 106 (1) operates as a first detection device, and detects low precision or simple information based on the capture information received from the sorting device 104 under conditions such as the presence or absence of an object, such as when there are many restrictions on the installation of the device. Detects objects in real time. Here, the detection device 106(1) is installed at the same location as the capture device 103 and the distribution device 104, which are installed near the communication area, or at a nearby location where data transfer does not take much time. As described above, the detection device 106 (1) has restrictions on the installation location, is smaller in scale, and has lower performance such as processing capacity than the detection device 106 (2) described later, so it cannot detect the presence or absence of an object in real time. Performs simple object detection.

The detection device 106 (2) operates as a second detection device, and detects object attributes other than object detection (for example, object Performs high-precision or advanced object detection in non-real time (measuring direction of movement, degree of crowding, number of objects, etc.). Here, the detection device 106(2) is installed far away from the capture device 103 and the distribution device 104, which are installed near the communication area. For this reason, the detection device 106(2) has fewer restrictions such as installation location and power supply, has higher performance such as processing power than the detection device 106(1), and is a large-scale device that can process large amounts of data at high speed. It is possible to install equipment and perform high-precision, advanced object detection processing and analysis that does not require real-time performance.

The network 107 corresponds to, for example, the Internet or a dedicated communication network that includes communication devices such as network switches, and when transferring a large amount of data, a time delay may occur. Therefore, the detection device 106(2) is not suitable for detecting an object that requires real-time performance, such as detecting the intrusion of the object 150 into a communication area.

In this way, in the object detection system 100 according to the present embodiment, the capture device 103 can capture the CSI transmitted from the STA 102 to the AP 101, and can detect objects within the communication area based on the captured information. In particular, in this embodiment, by distributing the captured CSI to the detection device 106(1) and the detection device 106(2), low-accuracy/simple object detection that requires real-time performance and high-precision object detection that does not require real-time performance are achieved.・It is possible to achieve both advanced object detection.

Note that in FIG. 1, the capture device 103, distribution device 104, storage device 105, and detection device 106(1) are described as separate devices to make the functions easier to understand. The functions of 105 may be integrated into one detection device 106(1). In this case, the information accumulated in the storage device 105 is transmitted from the detection device 106(1) to the detection device 106(2) via the network 107.

In addition, programs corresponding to the processes executed by the capture device 103, the distribution device 104, the storage device 105, the detection device 106(1), and the detection device 106(2) are installed on a computer or an integrated circuit such as an FPGA (Field Programmable Gate Array). You can also run it with Further, the program may be provided recorded on a storage medium or may be provided through a network.

(Example of sequence between AP101 and STA102)
FIG. 2 shows an example of a sequence of wireless signals communicated between the AP 101 and the STA 102.

In FIG. 2, the AP 101 broadcasts a VHT NDP Announcement frame as a start signal of a sounding protocol for acquiring CSI. Immediately thereafter, the AP 101 transmits VHT NDP including data for measuring CSI to the destination STA 102.

Here, VHT is an abbreviation for Very High Throughput, and the IEEE802.11ac standard is based on a VHT frame for performing ultra-high-speed communication. Further, NDP is an abbreviation for Null Data Packet, and VHT NDP is a frame that does not include communication data. The VHT NDP Announcement frame includes the addresses of the AP 101 and the destination STA 102, and is a frame for notifying the STA 102 of VHT NDP transmission in advance. Note that the VHT NDP Announcement frame is transmitted from one or more specific antennas, and even when transmitted from two or more antennas, the same data signal is transmitted from each antenna.

In FIG. 2, the STA 102 that receives the VHT NDP transmitted from the AP 101 derives a compressed CSI value using a method defined by IEEE802.11ac. The STA 102 stores the derived compressed CSI in a VHT Compressed Beamforming Report and transmits it. Here, the STA 102 can obtain CSI for each antenna of the AP 101, but as the number of antennas increases, the amount of CSI information fed back to the AP 101 increases. Therefore, a CSI (compressed CSI) selected from all CSIs is fed back to the AP 101 by a method predetermined in the wireless LAN standard.

Here, an example of an object detection method will be explained. In FIG. 1, the capture device 103 captures the CSI measured for each of the four antennas that is fed back from the STA 102 to the AP 101. For example, in FIG. 1, when the object 150 is moving in the direction of the dotted arrow, it invades the communication area from the AT(4) side of the AP 101. When the object 150 passes through to the AT(1) side, the CSI of AT(4) changes first, and the CSI changes temporally in the order of AT(3), AT(2), and AT(1). In this way, by detecting variations in the CSI for each antenna, it is possible to detect the intrusion and moving direction of the object 150.

The above-mentioned detection method is just an example, and it is not only possible to detect simple objects that require real-time performance such as intrusion detection, but also to detect real-time performance by analyzing a large amount of CSI accumulated over a predetermined period of time. This enables highly accurate and highly functional object detection, such as non-required people counting.

Here, as explained earlier, in the object detection system 100 according to the present embodiment, simple object detection that requires real-time performance such as intrusion detection is performed by the detection device 106 (1) installed near the communication area. ). Furthermore, highly accurate and highly functional object detection that does not require real-time performance, such as counting people, is performed by a high-performance detection device 106 (2) installed in a remote location.

In this way, the object detection system 100 according to the present embodiment can achieve both simple and low-precision object detection that requires real-time performance and advanced and high-precision object detection that does not require real-time performance.

(Example of object detection sequence)
FIG. 3 shows a sequence example of the object detection method according to this embodiment. Note that the sequence shown in FIG. 3 is executed by each device in FIG. 1.

In step (1), as explained in FIG. 2, communication is performed between the AP 101 and the STA 102. The capture device 103 monitors wireless LAN frames transmitted and received between the AP 101 and the STA 102.

In step (2), the capture device 103 captures a receivable wireless LAN frame, and captures a VHT Compressed Beamforming Report frame (a frame in which compressed CSI is stored) transmitted from a pre-designated STA 102 to the AP 101. ) is selected and captured.

In step (3), the capture device 103 transmits information about the frame in which the compressed CSI in the captured frame is stored and the reception time of the frame to the distribution device 104. Here, the capture device 103 includes its own number (a device-specific identifier such as a serial number) and transmits it to the distribution device 104 .

In step (4), the distribution device 104 transmits the frame containing the compressed CSI received from the capture device 103 and information on the reception time of the frame to the detection device 106(1) in real time.

In step (5), the detection device 106(1) performs object detection in real time based on the frame containing the compressed CSI received from the distribution device 104 and information on the reception time of the frame.

In step (6), in parallel with the processing in step (4), the distribution device 104 provides information on the frame in which the compressed CSI received from the capture device 103 in step (3) is stored and the reception time of the frame. , and the number of the capture device 103 are stored in the storage device 105. Note that the distribution device 104 may transmit the information stored in the storage device 105 to the detection device 106(2) in real time.

In step (7), the storage device 105 stores information such as the frame in which the compressed CSI output from the distribution device 104 is stored, the reception time of the frame, and the number of the capture device 103.

In step (8), similarly to step (2), only the VHT Compressed Beamforming Report frame transmitted from the STA 102 to the AP 101 is selected and captured again.

In step (9), similarly to step (3), the capture device 103 collects information such as the frame in which the compressed CSI is stored in the captured frame, information on the reception time of the frame, and the number of the capture device 103 itself. information is transmitted to the sorting device 104.

In step (10), similar to step (6), the distribution device 104 stores the frame in which the compressed CSI received from the capture device 103 in step (9), the information on the reception time of the frame, and the capture Information such as the number of the device 103 is stored in the storage device 105. Here, the distribution device 104 does not perform the same process as step (4), so the captured information is not transferred to the detection device 106(1). Note that the distribution device 104 may transmit the information stored in the storage device 105 to the detection device 106(2) in real time.

In step (11), similarly to step (7), the storage device 105 stores the frame in which the compressed CSI output from the distribution device 104 is stored, information on the reception time of the frame, and the number of the capture device 103. Accumulate information such as. Note that information stored in the storage device 105 will be explained later.

In step (12), the operations from step (1) to step (11) are repeated. In the example of FIG. 3, the sorting device 104 sends the capture information captured in step (2) to the detection device 106(1) in step (4), but the capture information captured in step (8) is not detected. Do not send to device 106(1). In other words, in step (12), the distribution device 104 repeats the process of decimating the number of transmissions of the capture information received from the capture device 103 by half and transmitting it to the detection device 106(1) once every two times. Execute. In the example of FIG. 3, the number of times of transmission to the detection device 106(1) is thinned out to 1/2, but it may be thinned out to any number of times, such as 1/3. Alternatively, a predetermined number (n pieces (n is a positive integer)) of capture information may be transmitted starting from the beginning of capture information captured within a certain period of time.

In step (13), the distribution device 104 reads the capture information stored in the storage device 105 and transmits it to the detection device 106(2) in non-real time. In the example of FIG. 3, the sorting device 104 reads out the capture information accumulated in the storage device 105 during the period when the operations from step (1) to step (11) are repeated, and sends it to the detection device 106(2). Send. That is, the distribution device 104 reads the capture information stored in the storage device 105 and transmits it to the detection device 106(2) at predetermined fixed time intervals or at predetermined times. Note that the distribution device 104 may transmit capture information to the detection device 106(2) every time it receives capture information from the capture device 103.

In step (14), the detection device 106(2) performs object detection based on information such as the CSI and reception time received from the distribution device 104 via the network 107. Note that the object detection performed by the detection device 106 (2) is more accurate object detection than the detection device 106 (1), and includes, for example, detection of the exact position and direction of movement of the object, and detection of the degree of congestion in the communication area. , high-precision or advanced object detection, including at least counting the number of objects and people, and advanced analysis, such as temporal and spatial trends and predictions of detection results, are performed in non-real time. Here, since the detection device 106(2) is a device with higher performance than the detection device 106(1), if the communication band of the network 107 between the distribution device 104 and the detection device 106(2) can be secured, It is also possible to sequentially receive capture information from the distribution device 104 and process it in real time.

In this way, the object detection system 100 according to the present embodiment uses the detection device 106 (1) to perform simple object detection that requires real-time performance, and uses the detection device to perform highly accurate and highly functional object detection that does not require real-time performance. 106(2), it is possible to achieve both simple and low-precision object detection that requires real-time performance and advanced and high-precision object detection that does not require real-time performance.

(Example of format of storage device 105)
FIG. 4 shows an example of a format in which information such as the CSI and reception time received from the capture device 103 is stored in the storage device 105.

The format of the information stored in the storage device 105 includes the reception time when the capture device 103 captured the CSI, the address of the AP 101, the address of the STA 102, the number of the capture device 103, and the CSI captured by the capture device 103 (acquired CSI). Information is stored in storage device 105.

Note that the respective addresses of the AP 101 and the STA 102 are acquired as the source address and destination address of the wireless frame in which the CSI is stored. Further, the number of the capture device 103 is a number unique to the capture device 103, and the number of the capture device 103 is added to the information transmitted to the distribution device 104. The number of the capture device 103 is used to identify each capture device 103 when a plurality of capture devices 103 are arranged.

In the example of FIG. 4, the CSI sent from the STA 102 with the address 11:22:33:44:55:66 to the AP 101 with the address AA:BB:CC:DD:EE:FF is received at 14:00:00. is captured by the capture device 103 with device number A1. The CSIs acquired at this time are, for example, φ11, φ21, . Similarly, the CSI captured by the capture device 103 is stored in the storage device 105 in chronological order, such as reception time 14:00:01 and reception time 14:00:02. Note that the acquired CSI will be described later.

In addition, in the example of FIG. 4, to make the explanation easier to understand, the reception time is assumed to be every 1 sec, and the CSI is captured every 1 sec. good.

Further, the example in FIG. 4 shows a case where one AP 101 and one STA 102 described in FIG. The same applies to the AP 101.

Note that even if multiple STAs 102 exist, if only one target STA 102 is set in the capture device 103, only the CSI information that the target STA 102 measures and sends to the AP 101 is captured. and stored in the storage device 105.

(Example of compressed CSI)
FIG. 5 shows an example of compressed CSI transmitted from the STA 102 to the AP 101. In FIG. 5, the number of transmitting antennas (the number of antennas of the AP 101) x the number of receiving antennas (the number of antennas of the STA 102), the number of compressed CSIs, and an example of the compressed CSIs are listed in order from the left column. Note that the number of transmitting antennas is two or more.

Here, as described above, the CSI between each antenna is measured according to the number of antennas of the STA 102 and the number of antennas of the AP 101. For this reason, as the number of antennas increases, the amount of CSI information fed back to the AP 101 becomes enormous, so the CSI (compressed CSI) selected from the CSI between all antennas according to the conditions determined by the wireless LAN standard is The compressed beamforming report frame is fed back to the AP 101.

For example, when the number of transmitting antennas is two and the number of receiving antennas is one (written as 2×1), the number of compressed CSIs is 2, and the compressed CSIs are φ11 and φ21. Similarly, in the case of 2×2, the number of compressed CSI is 2, and the compressed CSI is φ11, ψ21, and in the case of 3×1, the number of compressed CSI is 4, and the compressed CSI is φ11. , φ21, ψ21, and ψ31. Here, φij corresponds to phase information between the transmitting antenna number i (i is an integer of 2 or more) and the receiving antenna number j (j is an integer of 1 or more). ψij corresponds to amplitude information between transmitting antenna number i and receiving antenna number j. Similarly, compressed CSI is determined according to the combination of the number of transmitting antennas and the number of receiving antennas.

In the object detection system 100 according to the present embodiment shown in FIG. 1, the number of transmitting antennas is the number of antennas of the AP 101 (four), and the number of receiving antennas is the number of antennas of the STA 102 (one). In this case, a total of eight CSIs including four phase information and four amplitude information for each of the four antennas of the AP 101 are measured. Then, six compressed CSIs (φ11, φ21, φ31, ψ21, ψ31, ψ41) are calculated from the eight measured CSIs, as shown in 4×1 in Figure 5, and the calculated compressed CSI is transmitted to the AP 101.

Here, the compressed CSI shown in FIG. 5 is an example. In the above case, φ11 indicates the phase difference when the signals transmitted from AT(4) and AT(1) are received by the antenna of STA102. Similarly, φ21 represents the phase difference between AT(4) and AT(2), and φ31 represents the phase difference between AT(4) and AT(3). Note that φijε[0, 2π), where i and j are positive integers. In addition, ψ21 is the value expressed in angle of the amplitude ratio when the signals transmitted from AT(1) and AT(2) are received by the antenna of STA102 (tan-1 of the ratio of absolute values of amplitudes). value). Similarly, ψ21 represents the amplitude ratio between AT(1) and AT(2), and ψ31 represents the amplitude ratio between AT(1) and AT(3). Note that ψijε[0, π/2), where i and j are positive integers.

In this way, the STA 102 measures the CSI based on the reference signal transmitted from the AP 101 and transmits the compressed CSI to the AP 101. The capture device 103 captures the compressed CSI sent from the STA 102 to the AP 101 and sends it to the distribution device 104. The distribution device 104 transmits a portion of the compressed CSI received from the capture device 103 to the detection device 106(1), and transmits all of the CSI received from the capture device 103 to the detection device 106(2).

Here, in this embodiment, as shown in FIG. 1, the position of the capture device 103 is near the middle between the AP 101 and the STA 102, but it may be located anywhere as long as it can receive a signal from the STA 102. Furthermore, a configuration in which the functions of the capture device 103, the storage device 105, and the detection device 106 are included in the AP 101 or the STA 102 is also conceivable. Further, although there is one STA 102 in FIG. 1, there may be a plurality of STA 102. Further, the present embodiment may be applied to communication between the AP 101 and another AP 101 (in this case, one AP 101 functions as the STA 102).

As described above, the object detection system 100 according to the present embodiment performs sensing that requires real-time performance such as intrusion detection locally, and performs highly accurate and highly functional sensing such as counting people. In such cases, wireless information is transmitted to a remote location and detected remotely. This makes it possible to reduce or eliminate restrictions on installation location by performing sensing with low requirements for accuracy/function using low-performance equipment, and by performing sensing with high requirements in a remote location. This makes it possible to implement the project without being restricted by.

In particular, in this embodiment, by using two detection devices, the detection device 106(1) and the detection device 106(2), low-accuracy or simple object detection is possible in places where installation conditions or available power are limited. It becomes possible to perform high-precision or advanced detection (detecting the direction of movement of objects, measuring the degree of crowding, and the number of objects) using detection devices installed in locations where there are few restrictions on installation conditions or available power. Further, by providing the storage device 105 in the sorting device 104, it becomes possible to perform object detection with high accuracy without requiring real-time performance.

Here, programs corresponding to the processing performed by the sorting device 104, the detection device 106(1), and the detection device 106(2), respectively, are executed on a general-purpose computer or an integrated circuit such as an FPGA (Field Programmable Gate Array). It's okay. Further, the program may be provided recorded on a storage medium or may be provided through a network.

As described above, the object detection system, object detection method, and data sorting device according to the present invention, when detecting an object within a communication area from propagation path information of a wireless signal, combine propagation path information for object detection into a plurality of objects. By distributing the information to the object detection device, it is possible to achieve both low-accuracy, simple object detection that requires real-time performance, and high-accuracy, advanced object detection that does not require real-time performance.

100... Object detection system; 101... AP; 102... STA; 103... Capture device; 104... Sorting device; 105... Storage device; 106 (1), 106 (2) ...Detection device; 107...Network; 150...Object

Claims (8)

a capture device that captures propagation path information measured and communicated between two or more wireless devices;
a distribution device that distributes a part of the propagation path information captured by the capture device to a first detection device and all of the propagation path information to a second detection device;
The first detection device detects an object within a communication area between the wireless devices based on a portion of the propagation path information distributed by the distribution device,
The second detection device performs processing with higher accuracy and higher functionality than the first detection device based on all the propagation path information distributed from the distribution device, and improves the communication area between the wireless devices. An object detection system characterized by detecting objects inside. The object detection system according to claim 1,
The distribution device thins out the number of transmissions of the captured propagation path information to the first detection device and transmits the captured propagation path information in real time, and transmits the captured propagation path information to the second detection device. Transmit all propagation path information in real time or non-real time,
The first detection device is installed in a place where there are many restrictions on installation, and performs low-accuracy or simple object detection including the presence or absence of an object in real time,
The second detection device is installed in a place where there are few restrictions on installation, and performs high-precision or advanced object detection in non-real time, including at least one of detecting the moving direction of objects, measuring the degree of crowding, and the number of objects. An object detection system featuring: The object detection system according to claim 1 or 2,
The sorting device is
comprising a storage unit for storing information including at least the propagation path information received from the capture device,
An object detection system characterized in that information including at least the propagation path information stored in the storage unit is transmitted to the second detection device at predetermined constant time intervals. a capture device that captures propagation path information measured and communicated between two or more wireless devices;
a distribution device that distributes a part of the propagation path information captured by the capture device to a first detection device and all of the propagation path information to a second detection device;
The first detection device detects an object within a communication area between the wireless devices based on a portion of the propagation path information distributed by the distribution device,
The second detection device performs processing with higher accuracy and higher functionality than the first detection device based on all the propagation path information distributed from the distribution device, and improves the communication area between the wireless devices. An object detection method characterized by detecting an object within. In the object detection method according to claim 4,
The distribution device thins out the number of transmissions of the captured propagation path information to the first detection device and transmits the captured propagation path information in real time, and transmits the captured propagation path information to the second detection device. Transmit all propagation path information in real time or non-real time,
The first detection device is installed in a place where there are many restrictions on installation, and performs low-accuracy or simple object detection including the presence or absence of an object in real time,
The second detection device is installed in a place where there are few restrictions on installation, and performs high-precision or advanced object detection in non-real time, including at least one of detecting the moving direction of objects, measuring the degree of crowding, and the number of objects. An object detection method characterized by: In the object detection method according to claim 4 or 5,
The sorting device is
comprising a storage unit for storing information including at least the propagation path information received from the capture device,
An object detection method, comprising transmitting information including at least the propagation path information stored in the storage unit to the second detection device at predetermined constant time intervals. A capture device detects an object within a communication area between two or more wireless devices based on propagation path information measured and communicated between the two or more wireless devices. In a data distribution device that distributes the propagation path information,
A part of the captured propagation path information is transmitted to the first detection device in real time, and all of the captured propagation path information is transmitted in real time or to the second detection device. A data distribution device characterized by having a distribution section that transmits data in non-real time. The data sorting device according to claim 7,
comprising a storage unit for storing information including at least the propagation path information received from the capture device,
A data distribution device characterized in that information including at least the propagation path information stored in the storage unit is transmitted to the second detection device at predetermined constant time intervals.

Images